Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    night and day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.09
    et
    1.00
    2
    0.89
    ल
    0.89
    1
    0.85
     on
    0.79
    us
    0.78
    ’
    0.77
        
    0.76
    ל
    0.75
    POSITIVE LOGITS
     الليل
    0.95
    F
    0.86
    凌晨
    0.85
     रात्री
    0.85
     siang
    0.84
     nighttime
    0.84
     daytime
    0.84
    night
    0.83
    час
    0.83
     noct
    0.82
    Act Density 0.061%

    No Known Activations